feat(fusion_helpdesk_central): findings-first wizard, explicit Generate button

The old flow fired OpenAI on wizard open with just ticket + chatter,
so the AI summary was just a paraphrase of what the user originally
reported — your engineering analysis (scope, limitations, recommended
approach) never made it to the owner. Restructure to a two-step flow:

  1. Open wizard → empty findings + empty summary, NO OpenAI call
  2. You write findings: scope / effort / approach / risk
  3. Click 'Generate Summary from Findings' → OpenAI runs with
     ticket + chatter + findings, where the prompt explicitly tells
     the model to weight findings MORE THAN the original report
  4. Review/edit, then Send

Bulk wizard mirrors the flow per line: each row gets its own
findings + summary, one 'Generate All Summaries' button fans out
parallel OpenAI calls using each line's own findings.

Updated SUMMARY_PROMPT to:
- Tell the model the support engineer's findings are authoritative
- Emit a bullet structure that leads with the recommendation, not
  the user's restated ask
- Side with findings over the original report when they conflict

New tests cover:
- default_get does NOT fire OpenAI (regression guard for auto-AI)
- Findings text actually reaches the OpenAI prompt
- Send works with a manually-typed summary (no AI in the loop)
- Existing bulk + validation paths still pass with the new shape

Also folds in the deferred code-review #7: ThreadPoolExecutor now
explicitly cancels pending futures on timeout via
shutdown(wait=False, cancel_futures=True) so a slow OpenAI day can't
hold the wizard open for ceil(N/workers)*15s.

Bumps fusion_helpdesk_central to 19.0.2.3.0.

Smoke-tested live on nexa: opening the wizard makes zero OpenAI calls;
clicking Generate with findings='My findings: scope is XL, ~8h' makes
exactly one call and the findings text is verifiably in the prompt
body received by call_openai_chat.

fusion_helpdesk_central/tests/test_utils.py

@@ -54,6 +54,19 @@ class TestBuildSummaryPrompt(TransactionCase):
         # survives; '(empty)' marker keeps the model honest.
         self.assertIn('(empty)', prompt)
 
+    def test_findings_included_in_prompt(self):
+        # Findings is the support engineer's analysis — must reach OpenAI.
+        prompt = build_summary_prompt(
+            't', 'd', [], findings='Scope is small. ~2h of work.',
+        )
+        self.assertIn('Scope is small. ~2h of work.', prompt)
+
+    def test_findings_absent_uses_explicit_marker(self):
+        # Empty findings collapses to an explicit marker so the model
+        # doesn't read a blank section as "missing".
+        prompt = build_summary_prompt('t', 'd', [], findings='')
+        self.assertIn('none provided', prompt)
+
 
 @tagged('post_install', '-at_install', 'fusion_helpdesk_central')
 class TestTruncateForOpenAI(TransactionCase):